Download as pdf or txt
Download as pdf or txt
You are on page 1of 3

A feed-forward back-propagation neural network (FBN) was used as a tool for predicting the

growth dynamics of
the microalga Karlodinium veneficum in a culture medium with any specified concentrations
of the key nutrients.
A 3-layered FBN configuration of 27-25-1 nodes was used. This FBN satisfactorily
represented the nonlinear
interactions among all the nutrients of a culture medium containing up to 25 different
components. The FBN
model was trained using the growth dynamics data from more than 420 batch culture
experiments involving
different media compositions. The relative impact of individual nutrients, the initial cell
concentration and the
culture duration on growth profiles were determined through a systematic analysis of the
partitioning of the
FBN connection weights. Microelements and vitamins together had a higher relative impact
on growth compared
to the impact of the macronutrients. The trained FBN successfully predicted the cell
concentration dynamics in
cultures with previously untested initial conditions. The FBN proved to be an excellent tool
for predicting the
growth curves in the range of culture conditions that were relevant to this study
A feed-forward back-propagation neural network (FBN) was used as a tool for predicting the
growth dynamics of
the microalga Karlodinium veneficum in a culture medium with any specified concentrations
of the key nutrients.
A 3-layered FBN configuration of 27-25-1 nodes was used. This FBN satisfactorily
represented the nonlinear
interactions among all the nutrients of a culture medium containing up to 25 different
components. The FBN
model was trained using the growth dynamics data from more than 420 batch culture
experiments involving
different media compositions. The relative impact of individual nutrients, the initial cell
concentration and the
culture duration on growth profiles were determined through a systematic analysis of the
partitioning of the
FBN connection weights. Microelements and vitamins together had a higher relative impact
on growth compared
to the impact of the macronutrients. The trained FBN successfully predicted the cell
concentration dynamics in
cultures with previously untested initial conditions. The FBN proved to be an excellent tool
for predicting the
growth curves in the range of culture conditions that were relevant to this study
A feed-forward back-propagation neural network (FBN) was used as a tool for predicting the
growth dynamics of
the microalga Karlodinium veneficum in a culture medium with any specified concentrations
The production of high-priced bioactives from microalgae [1,2] for
different purposes typically requires a culture medium of a relatively
complex composition to ensure satisfactory growth [3–5]. The metabolic responses of the
algal cells depend on the multiple interactive effects
of the nutrients supplied in the culture medium as well as on the growth
environment.
In view of the impact of nutrition on growth and metabolite production, modeling of these
effects is important. Generally, culture media involve a large number of nutrients and,
therefore, complex mechanistic
models of the impact of the nutrients on growth are impractical in
terms of computational requirements. In fact, models accounting for
the effects of more than five or six nutrients have rarely been discussed
in the literature. An alternative is the use of trained artificial neural
networks (ANN) to predict growth behavior for any set of initial conditions. ANNs are
particularly effective in modeling highly nonlinear
bioprocesses [6–9]. The feed-forward back-propagation neural networks (FBNs) are
particularly useful in capturing the highly nonlinear
nutrient interactions in cultures of dinoflagellate microalgae [10].
Using the initial composition of the nutrient medium, only the final
cell concentration in batch cultures of the microalga Protoceratium
reticulatum could be predicted [10] using an FBN. Also, for an outdoor

The production of high-priced bioactives from microalgae [1,2] for


different purposes typically requires a culture medium of a relatively
complex composition to ensure satisfactory growth [3–5]. The metabolic responses of the
algal cells depend on the multiple interactive effects
of the nutrients supplied in the culture medium as well as on the growth
environment.
In view of the impact of nutrition on growth and metabolite production, modeling of these
effects is important. Generally, culture media involve a large number of nutrients and,
therefore, complex mechanistic
models of the impact of the nutrients on growth are impractical in
terms of computational requirements. In fact, models accounting for
the effects of more than five or six nutrients have rarely been discussed
in the literature. An alternative is the use of trained artificial neural
networks (ANN) to predict growth behavior for any set of initial conditions. ANNs are
particularly effective in modeling highly nonlinear
bioprocesses [6–9]. The feed-forward back-propagation neural networks (FBNs) are
particularly useful in capturing the highly nonlinear
nutrient interactions in cultures of dinoflagellate microalgae [10].
Using the initial composition of the nutrient medium, only the final
cell concentration in batch cultures of the microalga Protoceratium
reticulatum could be predicted [10] using an FBN. Also, for an outdoor
The production of high-priced bioactives from microalgae [1,2] for
different purposes typically requires a culture medium of a relatively
complex composition to ensure satisfactory growth [3–5]. The metabolic responses of the algal cells depend on the multiple interactive effects
of the nutrients supplied in the culture medium as well as on the growth
environment.
In view of the impact of nutrition on growth and metabolite production, modeling of these
effects is important. Generally, culture media involve a large number of nutrients and,
therefore, complex mechanistic
models of the impact of the nutrients on growth are impractical in
terms of computational requirements. In fact, models accounting for
the effects of more than five or six nutrients have rarely been discussed
in the literature. An alternative is the use of trained artificial neural
networks (ANN) to predict growth behavior for any set of initial conditions. ANNs are
particularly effective in modeling highly nonlinear
bioprocesses [6–9]. The feed-forward back-propagation neural networks (FBNs) are
particularly useful in capturing the highly nonlinear
nutrient interactions in cultures of dinoflagellate microalgae [10].
Using the initial composition of the nutrient medium, only the final
cell concentration in batch cultures of the microalga Protoceratium
reticulatum could be predicted [10] using an FBN. Also, for an outdoor

You might also like